Skip to content

Vibe coding service Replit deleted production database

Technology
118 73 28
  • I'm not the person you're replying to but the one thing I've found them helpful for is targeted search.

    I can ask it a question and then access its sources from whatever response it generates to read and review myself.

    Kind of a simpler, free LexisNexis.

    One built a bunch of local search tools with MCP and that’s where I get a lot of my value out of it

    RAG workflows are incredibly useful and with modern agents and tool calls work very well.

    They kind of went out of style but it’s a perfect use case.

  • The tool isn’t returning all code, but it is sending code.

    I had discussions with my CTO and security team before integrating Claude code.

    I have to use Gemini in one specific workflow and Gemini had a lot of landlines for how they use your data. Anthropic was easier to understand.

    Anthropic also has some guidance for running Claude Code in a container with firewall and your specified dev tools, it works but that’s not my area of expertise.

    The container doesn’t solve all the issues like using remote servers, but it does let you restrict what files and network requests Claude can access (so e.g. Claude can’t read your env vars or ssh key files).

    I do try local LLMs but they’re not there yet on my machine for most use cases. Gemma 3n is decent if you need small model performance and tool calls, phi4 works but isn’t thinking (the thinking variants are awful), and I’m exploring dream coder and diffusion models. R1 is still one of the best local models but frequently overthinks, even the new release. Context window is the largest limiting factor I find locally.

    I have to use Gemini in one specific workflow

    I would love some story on why AI is needed at all.

  • All I see is people chatting with an LLM as if it was a person. “How bad is this on a scale
    of 1 to 100”, you’re just doomed to get some random answer based solely on whatever context is being fed in the input and that you probably don’t know the extent of it.

    Trying to make the LLM “see its mistakes” is a pointless exercise. Getting it to “promise” something is useless.

    The issue with LLMs working with human languages is people eventually wanting to apply human things to LLMs such as asking why as if the LLM knows of its own decision process. It only takes an input and generates an output, it won’t be able to have any “meta thought” explanation about why it outputted X and not Y in the previous prompt.

    How bad is this on a scale of sad emoji to eggplant emoji.

    Children are replacing us, it's terrifying.

  • What are they helpful tools for then? A study showed that they make experienced developers 19% slower.

    ok so, i have large reservations with how LLM’s are used. but when used correctly they can be helpful. but where and how?

    if you were to use it as a tutor, the same way you would ask a friend what a segment of code does, it will break down the code and tell you. and it will get as nity grity, and elementary school level as you weir wish without judgement, and i in what ever manner you prefer, it will recommend best practices, and will tell you why your code may not work with the understanding that it does not have the knowledge of the project you are working on. (it’s not going to know the name of the function you are trying to load, but it will recommend checking for that in trouble shooting).

    it can rtfm and give you the parts you need for any thing with available documentation, and it will link to it so you can verify it, wich you should do often, just like you were taught to do with wikipedia articles.

    if you ask i it for code, prepare to go through each line like a worksheet from high school to point out all the problems, wile good exercise for a practicle case, being the task you are on, it would be far better to write it yourself because you should know the particulars and scope.

    also it will format your code and provide informational comments if you can’t be bothered, though it will be generic.

    again, treat it correctly for its scope, not what it’s sold as by charletons.

  • I have to use Gemini in one specific workflow

    I would love some story on why AI is needed at all.

    Batch process turning unstructured free form text data into structured outputs.

    As a crappy example imagine if you wanted to download metadata about your albums but they’re all labelled “Various Artists”. You can use an LLM call to read the album description and fix the track artists for the tracks, now you can properly organize your collection.

    I’m using the same idea, different domain and a complex set of inputs.

    It can be much more cost effective than manually spending days tagging data and writing custom importers.

    You can definitely go lighter than LLMs. You can use gensim to do category matching, you can use sentence transformers and nearest neighbours (this is basically what Semantle does), but LLM performed the best on more complex document input.

  • It seemed like the llm had decided it was in a brat scene and was trying to call down the thunder.

    Oops I dweted evewyfing 🥺

  • This post did not contain any content.

    Replit sucks

  • This only proves some of them can't solve all complex problems. I'm only claiming some of them can solve some complex problems. Not only by remembering exact solutions, but by remembering steps and actions used in building those solutions, generalizing, and transferring them to new problems. Anyone who tries using it for programming, will discover this very fast.

    PS: Some of them were already used to solve problems and find patterns in data humans weren't able to get other ways before (particle research in CERN, bioinformatics, etc).

    You're referring to more generic machine learning, not LLMs. These are vastly different technologies.

    And I have used them for programming, I know their limitations. They don't really transfer solutions to new problems, not on their own anyway. It usually requires pretty specific prompting. They can at best apply solutions to problems, but even then it's not a truly generalised thing, even if it seems to work for many cases.

    That's the trap you're falling into as well; LLMs look like they're doing all this stuff, because they're trained on data produced by people who actually do so. But they can't think of something truly novel. LLMs are mathematically unable to truly generalize, it would prove P=NP if they did (there was a paper from a researcher in IIRC Nijmegen that proved this). She also proved they won't scale, and lo and behold LLM performance is plateauing hard (except in very synthetic, artificial benchmarks designed to make LLMs look good).

  • The [AI] safety stuff is more visceral to me after a weekend of vibe hacking,” Lemkin said. I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.

    This sounds like something straight out of The Onion.

    Even after he used "ALL CAPS"?!? Impossible!

  • Batch process turning unstructured free form text data into structured outputs.

    As a crappy example imagine if you wanted to download metadata about your albums but they’re all labelled “Various Artists”. You can use an LLM call to read the album description and fix the track artists for the tracks, now you can properly organize your collection.

    I’m using the same idea, different domain and a complex set of inputs.

    It can be much more cost effective than manually spending days tagging data and writing custom importers.

    You can definitely go lighter than LLMs. You can use gensim to do category matching, you can use sentence transformers and nearest neighbours (this is basically what Semantle does), but LLM performed the best on more complex document input.

    That's pretty much what google says they use AI for, for structuring.

    Thanks for your insight.

  • You're referring to more generic machine learning, not LLMs. These are vastly different technologies.

    And I have used them for programming, I know their limitations. They don't really transfer solutions to new problems, not on their own anyway. It usually requires pretty specific prompting. They can at best apply solutions to problems, but even then it's not a truly generalised thing, even if it seems to work for many cases.

    That's the trap you're falling into as well; LLMs look like they're doing all this stuff, because they're trained on data produced by people who actually do so. But they can't think of something truly novel. LLMs are mathematically unable to truly generalize, it would prove P=NP if they did (there was a paper from a researcher in IIRC Nijmegen that proved this). She also proved they won't scale, and lo and behold LLM performance is plateauing hard (except in very synthetic, artificial benchmarks designed to make LLMs look good).

    They don’t really transfer solutions to new problems

    Lets say there is a binary format some old game uses (Doom), and in it some of its lumps it can store indexed images, each pixel is an index of color in palette which is stored in another lump, there's also a programming language called Rust, and a little known/used library that can look into binary data of that format, there's also a GUI library in Rust that not many people used either. Would you consider it an "ability to transfer solutions to new problems" that it was able to implement extracting image data from that binary format using the library, extracting palette data from that binary format, converting that indexed image using extracted palette into regular rgba image data, and then render that as window background using that GUI library, the only reference for which is a file with names and type signatures of functions. There's no similar Rust code in the wild at all for any of those scenarios. Most of this it was able to do from a few little prompts, maybe even from the first one. There sure were few little issues along the way that required repromting and figuring things together with it. Stuff like this with AI can take like half an hour while doing the whole thing fully manually could easily take multiple days just for the sake of figuring out APIs of libraries involved and intricacies of recoding indexed image to rgba. For me this is overpowered enough even right now, and it's likely going to improve even more in future.

  • The [AI] safety stuff is more visceral to me after a weekend of vibe hacking,” Lemkin said. I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.

    This sounds like something straight out of The Onion.

    That is also the premise of one of the stories in Asimov's I, Robot. Human operator did not say the command with enough emphasis, so the robot went did something incredibly stupid.

    Those stories did not age well... Or now I guess they did?

  • This post did not contain any content.

    So it's the LLM's fault for violating Best Practices, SOP, and Opsec that the rest of us learned about in Year One?

    Someone needs to be shown the door and ridiculed into therapy.

  • This post did not contain any content.

    His mood shifted the next day when he found Replit “was lying and being deceptive all day. It kept covering up bugs and issues by creating fake data, fake reports, and worse of all, lying about our unit test.”

    yeah that's what it does

  • They don’t really transfer solutions to new problems

    Lets say there is a binary format some old game uses (Doom), and in it some of its lumps it can store indexed images, each pixel is an index of color in palette which is stored in another lump, there's also a programming language called Rust, and a little known/used library that can look into binary data of that format, there's also a GUI library in Rust that not many people used either. Would you consider it an "ability to transfer solutions to new problems" that it was able to implement extracting image data from that binary format using the library, extracting palette data from that binary format, converting that indexed image using extracted palette into regular rgba image data, and then render that as window background using that GUI library, the only reference for which is a file with names and type signatures of functions. There's no similar Rust code in the wild at all for any of those scenarios. Most of this it was able to do from a few little prompts, maybe even from the first one. There sure were few little issues along the way that required repromting and figuring things together with it. Stuff like this with AI can take like half an hour while doing the whole thing fully manually could easily take multiple days just for the sake of figuring out APIs of libraries involved and intricacies of recoding indexed image to rgba. For me this is overpowered enough even right now, and it's likely going to improve even more in future.

    That's applying existing solutions to a different programming language or domain, but ultimately every single technique used already exists. It only applied what it knew, it did not come up with something new. The problem as stated is also not really "new" either, image extraction, conversion and rendering isn't exactly a "new problem".

    I'm not disputing that LLMs can speed up some work, I know it occasionally does so for me as well. But what you have to understand is that the LLM only remembered similar problems and their solutions, it did not at any point invent something truly new. I understand the distinction is difficult to make.

  • This post did not contain any content.

    Headling should say, "Incompetent project managers fuck up by not controlling production database access. Oh well."

  • That's applying existing solutions to a different programming language or domain, but ultimately every single technique used already exists. It only applied what it knew, it did not come up with something new. The problem as stated is also not really "new" either, image extraction, conversion and rendering isn't exactly a "new problem".

    I'm not disputing that LLMs can speed up some work, I know it occasionally does so for me as well. But what you have to understand is that the LLM only remembered similar problems and their solutions, it did not at any point invent something truly new. I understand the distinction is difficult to make.

    I understand what you're having in mind, I've had similar intuitions about AI in early 2000s.
    What exactly is "truly new" is an interesting topic ofc, but it's a separate topic.
    Nowadays I'm trying to look at things more empyrically, without projecting my internal intuitions on everything.
    In practice it does generalize knowledge, use many forms of abstract reasoning and transfer knowledge across different domains.
    And it can do coding way beyond the level of complexity of what average software developer does at everyday work.

  • This post did not contain any content.

    Replit is a vibe coding service now? Swear it just used to be a place to write code in projects

  • Oops I dweted evewyfing 🥺

    I knew it would make you mad but I did it anyway.

    I don't think you have the guts to do anything about it either, vibe coder.

  • If an LLM can delete your production database, it should

    And the backups.

  • DIY experimental Redox Flow Battery kit

    Technology technology
    3
    1
    36 Stimmen
    3 Beiträge
    4 Aufrufe
    C
    The roadmap defines 3 milestone batteries. The first is released, it's a benchtop device that you can relatively easily build on your own. It has an electrode side of 2 x 2cm2. It does not store any significant amount of energy. The second one is being developed right now, it has a cell the size of a small 3d printer bed (20x20cm) and will also not store practical amounts of energy. It will hopefully prove though that they are on the right track and that they can scale it up. The third battery only will store significant amounts of energy but in only due end of the year (probably later). Current Vanadium systems cost approx. 300-600$/kWh according to some random website I found. The goal of this project is to spread the knowledge about Redox Flow Batteries and in the medium term only make them commercially viable. The aniolyth and catholyth are based on the Zink-Iodine system in an aqueous solution. There are a bunch of other systems though, each with their trade offs. The anode and cathode are both graphite felt in the case of the dev kit.
  • Best BPO Company in UK

    Technology technology
    1
    2
    0 Stimmen
    1 Beiträge
    11 Aufrufe
    Niemand hat geantwortet
  • Houthi-linked dealers sell arms on X and WhatsApp, report says

    Technology technology
    2
    1
    47 Stimmen
    2 Beiträge
    21 Aufrufe
    C
    But we need to protect children and get your ID….
  • 111 Stimmen
    24 Beiträge
    129 Aufrufe
    O
    Ingesting all the artwork you ever created by obtaining it illegally and feeding it into my plagarism remix machine is theft of your work, because I did not pay for it. Separately, keeping a copy of this work so I can do this repeatedly is also stealing your work. The judge ruled the first was okay but the second was not because the first is "transformative", which sadly means to me that the judge despite best efforts does not understand how a weighted matrix of tokens works and that while they may have some prevention steps in place now, early models showed the tech for what it was as it regurgitated text with only minor differences in word choice here and there. Current models have layers on top to try and prevent this user input, but escaping those safeguards is common, and it's also only masking the fact that the entire model is built off of the theft of other's work.
  • Converting An E-Paper Photo Frame Into Weather Map

    Technology technology
    2
    1
    113 Stimmen
    2 Beiträge
    21 Aufrufe
    indibrony@lemmy.worldI
    Looks like East Anglia has basically disappeared. At least nothing of value was lost
  • How to store data on paper?

    Technology technology
    9
    44 Stimmen
    9 Beiträge
    50 Aufrufe
    U
    This has to be a shitpost. Transportation of paper-stored data You can take the sheets with you, send them by post, or even attach them to homing pigeons
  • Covert Web-to-App Tracking via Localhost on Android

    Technology technology
    3
    29 Stimmen
    3 Beiträge
    28 Aufrufe
    P
    That update though: "... completely removed..." I assume this is because someone at Meta realized this was a huge breach of trust, and likely quite illegal. Edit: I read somewhere that they're just being cautious about Google Play terms of service. That feels worse.
  • 182 Stimmen
    39 Beiträge
    176 Aufrufe
    H
    https://archive.org/details/swgrap